Questions tagged [machine-learning]

Machine learning algorithms build a model of the training data. The term "machine learning" is vaguely defined; it includes what is also called statistical learning, reinforcement learning, unsupervised learning, etc. ALWAYS ADD A MORE SPECIFIC TAG.

Filter by
Sorted by
Tagged with
1
vote
1answer
186 views

Recommendations for textbooks covering current data mining/machine learning techniques for fraud detection?

I work in the health insurance field, but a general treatment of fraud detection methodologies would still be helpful. So far I've discovered brief articles outlining particular techniques used in ...
1
vote
1answer
495 views

Activation Functions

In the linear regression models, the model prediction $y(x, w)$ is given by a linear function of the parameters $w$. In the simplest case, the model is also linear in the input variables and therefore ...
1
vote
1answer
669 views

How to process categorical features with many values? [duplicate]

I want to apply machine learning and deep learning. I have categorical data on string. My first option was to perform dummy encoding on the columns (scikitlearn). ...
1
vote
0answers
3k views

predicting time series with support vector machine using R

I am planning to do time series prediction using support vector Machine. I could not find any materials about time series application of support vector machines using R or Mat-lab. Similar question ...
1
vote
1answer
668 views

Cross validation accuracy is the same as the fraction of negative labels - what does it mean?

I have a dataset for classification (binary - 1/0) that has around 4000 samples that I use to train the model (I'm using an SVM, if that's relevant). To check whether everything is working fine, I ...
1
vote
1answer
114 views

Trees of ensembles.

I have a large dataset (100k+), and it's growing everyday. I want to train it to predict a value (a regression problem). I've been finding that ensemble trees work the best for now, but in the ...
1
vote
1answer
380 views

Representation input and output nodes in neural network for $\textit{AlphaZero}$ chess?

I am wondering how the neural network for AlphaZero chess works. I know that it takes a historic set of states of the board as input nodes. But I am wondering how many output nodes there are and what ...
1
vote
1answer
100 views

More features, less F-Score

Is there any rule about relationship between number of features and performance of the model? Recently, I did an experiment on 3 sets of features (all extracted from a same dataset). The strange point ...
1
vote
3answers
2k views

Decision tree for output prediction

I have satellite data that provides radiance which I use to compute the Flux (using surface and cloud info). Now using a regression method, I can develop a mathematical model directly relating ...
1
vote
1answer
300 views

Question about implementing nested Chinese Restaurant Process (nCRP)

I am trying to follow the original paper on nCRP by Blei et al., 2010 and am confused with it's implementation. The authors describe the analogy for an nCRP as follows: A tourist arrives at the ...
1
vote
2answers
548 views

Xgboost Feature Importance shift

If I plot the feature importance of my xgboost model I get for example f10,f3,f7,f99,... as the most important features. Now I decided to remove f3 and I imagined the new feature importance would be ...
1
vote
0answers
839 views

How should I use Recurrent Neural Network to model this problem? [closed]

I am using Keras to do a machine learning task: Let's say I want to predict the time that a user spends on a product page. Each training case is a partial user visit session. One single user may ...
1
vote
3answers
505 views

Which is the best classifier and with what performance measures?

I tried to implement a Classifier comparison like in the scikit-learn for text classification. I used an 81 instances as a training sample and a 46 instances as a test sample. I tried several ...
1
vote
1answer
236 views

Maximum Likelihood Estimate (MLE) equivalent to finding $\hat y$ in linear regression with i.i.d. Gaussian noise distribution

In an assignment I need to show that for linear regression, with the noise i.i.d. Gaussian distributed $\epsilon_i \sim N(0,\sigma^2)$, that finding the Maximum Likelihood Estimate (MLE) is equivalent ...
1
vote
1answer
106 views

Scaling in linear regression

The text is from Intro to Statistical Learning Page no 380.Can anyone explain the both ideas clearly with an example if possible 1) In linear regression scaling has no effect. 2)In linear ...
1
vote
0answers
220 views

Spearman rho statistical significance value (z)

How can I calculate the statistical significance (Z) of spearman's footrule rho? I came across the formula at this wiki page ...
1
vote
1answer
389 views

Is it reasonable to compare a regression model with machine learing algorithms using RMSE?

I have a 70K x 30 dataset and I want to build a regression model on it. Right now, I am running a bunch of algorithms via Weka tool with cross-validation and I compare the RMSE values reported by Weka ...
1
vote
1answer
256 views

CNN - Is this a Toeplitz Matrix?

I have been reading through Chapter 9 of www.deeplearningbbook.org, where convolutional networks are being described. The following image represents the output of a 2D convolution, without kernel ...
1
vote
1answer
104 views

Fit a function f on dataset X such that f(X) fits a histogram

I have dataset $X=\{\boldsymbol{x_1},\boldsymbol{x_2},\dots,\boldsymbol{x_n}\}$ and $Y=\{y_1,y_2,\dots,y_n\}$ and want to learn a function $f$ such that $y = f(\boldsymbol{x})$ can be approximated as ...
1
vote
1answer
597 views

Should I use the same weight initialization for each fold in cross validation?

Say, for example, I have 5 splits of my data. Can I randomly initialize the weights for my neural network at the start of each split? Or should I save the initial weights randomly initialized for the ...
1
vote
1answer
578 views

How to add more inputs to a CNN?

What would be the correct approach to add additional inputs that aren't images, e.g. time, to the CNN. I initially thought of adding more inputs to one of the densely connected layers at the end of ...
1
vote
1answer
3k views

Activation functions for autoencoder performing regression

I want to train both a single-layer autoencoder and a multi-layer autoencdoer in Keras to reconstruct an input with 24 features, all in the same scale with int values from 0 to ~200000. My question is:...
1
vote
0answers
61 views

How to grow a single tree model with continuous and categorical predictors?

I'm trying to implement the recursive binary splitting algorithm to grow a simple tree model. My aim is that it serves both for regression and classification trees. My problem is choosing which ...
1
vote
0answers
121 views

What cause $X\beta$ shift from Stochastic Gradient Descent Comparing to Logistic Regression?

I am experimenting with stochastic gradient descent and observing very strange output. In a toy problem, the $X\beta$ for stochastic gradient descent is always larger than $0$, which will be ...
1
vote
2answers
1k views

Rescaling input features for neural networks regression

In Neural Nets for the regression problem, we rescale the continuous labels consistently with the output activation function, i.e. normalize them if the logistic sigmoid is used, or adjusted normalize ...
1
vote
1answer
407 views

Should the resulting weight vector of SVM be of unit length?

In a tutorial on SVM by Andrew N.G http://cs229.stanford.edu/notes/cs229-notes3.pdf, on page 6,7 he has explained SVM in connection to functional margins and then has replaced it by 1 reasoning that W ...
1
vote
2answers
806 views

Variational inference: how to rewrite ELBO?

I am reading this paper on variational inference and this website. One thing I am confused about is how they get to decompose ELBO, where $ELBO(q) = E_q[log~p(z,x)] - E_q[log~q(z)]$, when focusing ...
1
vote
1answer
2k views

out of bag error in random forest and data partitioning

I have a question concerning OOB error in random forests and data partitioning. As far as i know in random forests the trees are not pruned. Also we use OOB error for measuring the performance of the ...
1
vote
3answers
4k views

Different results from several “passes” of Random Forest on same dataset

I've been playing around with the German Credit dataset available in Kuhn & Johnson's caret package for ...
1
vote
1answer
370 views

Can a random forest be 100% accurate using only 1 predictor that is not linearly separable?

A random forest classifier is reporting perfect classification accuracy when I pass it the data that it was trained on even though it has only 1 predictor that with overlapping values between classes. ...
1
vote
2answers
161 views

Regression on Predicting Time

If I have a dataset like this: ...
1
vote
0answers
653 views

How to represent outliers for multi dimensional data (local outlier factor)

Below graph taken from http://en.wikipedia.org/wiki/Local_outlier_factor displays "LOF scores : LOF image : This is great for two dimensional data but what about data > than two dimensions. How ...
1
vote
1answer
610 views

what is the correct formula of momentum for gradient descent?

I have been trying to get a better understanding of momentum, but in my search for clarification I got pretty confused. The main reason is that there seem to be multiple different, non-equivalent ...
1
vote
1answer
352 views

Is the true relation between independent and dependent variables assumed to be a function or a distribution?

In classification and regression tasks, we try to learn from a training data set a function mapping a independent variable $X$ to a dependent variable $Y$. When evaluating the error rate of a ...
1
vote
1answer
2k views

How does regularization work for a Gaussian Process classification model?

I'm a bit confused about Gaussian Process models for classification. In chapter 3 of http://www.gaussianprocess.org/gpml/ it is claimed that you can use a logit or probit model without any additional ...
1
vote
1answer
92 views

Understanding linear regression

In class we've seen that $a$ (the weights) must satisfy $$X^T (y-Xa) =0$$ Here $X$ is a $(n\times d)$ matrix (so we have $n$ samples in $\mathbb R^d$) let's denote the residuals $r = y-Xa$. In our ...
1
vote
1answer
109 views

Doubts on Hypothesis set?

Newbie to ML, i am having a hard time understanding what exactly is a hypothesis set. From what i understand: In Supervised Learning, we will be given Input, Output. We need to find a Hypothesis ...
1
vote
1answer
244 views

Identifying a stochastic trend model

My question is a bit general Say I am given a time series $X_t$, In what ways I can use in order to check whether the sequence behaves like a stochastic trend model or not? and if yes how can I find ...
1
vote
0answers
43 views

How to use random forest for regression after it is trained

I don't understand how to work with a random forest regressor after it is trained. I read and coded some tutorials about regression with random forests in Python with scikit but I don't understand how ...
1
vote
2answers
935 views

Confidence Interval - Binary classification [duplicate]

How do we calculate a confidence interval for a result in binary classifiers ? CI for regression problems makes sense since we have a variable estimated output that I can calculate its estimated mean ...
1
vote
2answers
2k views

How to normalize filters in convolutional neural networks?

Usually, when convolving images, the elements in the filter sum to one. Is this criterion enforced in convolutional neural networks? If yes, how?
0
votes
1answer
37 views

Expectation of matrix X multiply by indicator matrix

Let X1, . . . , Xn, X be i.i.d. R-valued random variables Suppose an indicator matrix I{A} be 1 if A is true and 0 otherwise. Then for τ > 0, and How this could be true....? Can anyone walk ...
0
votes
1answer
362 views

Feasibility of a neural network fitting a specific multivariate quadratic function? [duplicate]

I have run into some problems when trying to train a network that fits some multivariate quadratic function, or the Euclidean distance between 2 points in a 3-dimensional space, where they are 'pretty ...
0
votes
1answer
85 views

Should cross-validation be used to provide the final parameters, or just to compare models?

In Andrew Ng's Coursera class on Machine Learning, we learned to use a Gaussian distribution $p(x)=\prod^n_{j=1}p(x_j,μ_j,σ^2_j)$ to detect anomalous examples when $p(x)<\epsilon$ where $x_j$ are ...
0
votes
1answer
400 views

Can the distribution of emission probabilities of an HMM be swapped out for the re-estimated ones only after all training sequences have been covered?

Regarding the re-estimation procedure of the Baum-Welch algorithm, the sources I looked into so far all describe the process in an abstract manner. Therefore I am wondering the following about ...
0
votes
1answer
383 views

liblinear one vs rest learn parameters

Liblinear (http://www.csie.ntu.edu.tw/~cjlin/liblinear/) does not support for probability estimates. Say I have three classes C1, C2 and C3. I want to learn the model paramters for each 'one vs rest' ...
0
votes
2answers
1k views

Candidate-Elimination concept learning algorithm: specialising the general boundary

I'm reading about concept learning from Mitchell, and I've been looking at the Candidate-Elimination algorithm for identifying a hypothesis to fit a set of training data with binary labels The ...
0
votes
0answers
102 views

Why $\hat{f}$ and $\epsilon$ are independent, in bias-variance tradeoff proof?

Backgrounds I'm following Wiki page's proof of the bias-variance tradeoff. The page gives the following proof. Proof(ref) Denote $\hat{f}$ : an estimate of a deterministic function $f$, where ...
0
votes
1answer
449 views

Order of normalization / augmentation for image classification

I'm currently working on a common image classification with CNN. I would like to use both normalization (substract mean / divide by std per channel) and data augmentation (rotation, color, blur, ...) ...
0
votes
1answer
377 views

AdaBoost algorithm question

In the boosting algorithm,AdaBoost ,those observations which were misclassified by the classifier in the (m-1)th step have their weights increased in the mth step, and those which were correctly ...